Related papers: InnateCoder: Learning Programmatic Options with Fo…

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong…

Driving in the dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level…

When robots are deployed in the field for environmental monitoring they typically execute pre-programmed motions, such as lawnmower paths, instead of adaptive methods, such as informative path planning. One reason for this is that adaptive…

Quadratic programming is a workhorse of modern nonlinear optimization, control, and data science. Although regularized methods offer convergence guarantees under minimal assumptions on the problem data, they can exhibit the slow…

Model-free reinforcement learning algorithms can compute policy gradients given sampled environment transitions, but require large amounts of data. In contrast, model-based methods can use the learned model to generate new data, but model…

Methods to learn under algorithmic triage have predominantly focused on supervised learning settings where each decision, or prediction, is independent of each other. Under algorithmic triage, a supervised learning model predicts a fraction…

Recent robot learning methods commonly rely on imitation learning from massive robotic dataset collected with teleoperation. When facing a new task, such methods generally require collecting a set of new teleoperation data and finetuning…

OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the…

Deep reinforcement learning has enabled robots to learn motor skills from environmental interactions with minimal to no prior knowledge. However, existing reinforcement learning algorithms assume an episodic setting, in which the agent…

Safety is a critical feature of controller design for physical systems. When designing control policies, several approaches to guarantee this aspect of autonomy have been proposed, such as robust controllers or control barrier functions.…

Efficiently training control policies for robots is a major challenge that can greatly benefit from utilizing knowledge gained from training similar systems through cross-embodiment knowledge transfer. In this work, we focus on accelerating…

The ability to think abstractly and reason by analogy is a prerequisite to rapidly adapt to new conditions, tackle newly encountered problems by decomposing them, and synthesize knowledge to solve problems comprehensively. We present…

We present a method for learning options from segmented demonstration trajectories. The trajectories are first segmented into skills using nonparametric Bayesian clustering and a reward function for each segment is then learned using…

We introduce a new way of learning to encode position information for non-recurrent models, such as Transformer models. Unlike RNN and LSTM, which contain inductive bias by loading the input tokens sequentially, non-recurrent models are…

Visual domain randomization in simulated environments is a widely used method to transfer policies trained in simulation to real robots. However, domain randomization and augmentation hamper the training of a policy. As reinforcement…

Modern data-driven machine learning system designs exploit inductive biases in architectural structure, invariance and equivariance requirements, task-specific loss functions, and computational optimization tools. Previous works have…

Machine translation is a natural candidate problem for reinforcement learning from human feedback: users provide quick, dirty ratings on candidate translations to guide a system to improve. Yet, current neural machine translation training…

Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental…

Inductive logic programming is a type of machine learning in which logic programs are learned from examples. This learning typically occurs relative to some background knowledge provided as a logic program. This dissertation introduces…

Recent advances in batch (offline) reinforcement learning have shown promising results in learning from available offline data and proved offline reinforcement learning to be an essential toolkit in learning control policies in a model-free…